Stochastic fluid models have been applied to model and evaluate the performance of many important real systems. The automatic analysis tools to support of fluid models are still not as improved as the ones for discrete state Markov models, but there is a wide range of models which can be effectively described and analyzed with fluid models. Also the model support of hybrid models from various performance evaluation tools improves continuously. The aim of this work is to summarize the basic concepts and the potential use of Markov fluid models. The factors which determine the limits of solvability of fluid models are also discussed. Practical guidelines can be extracted from these factors to determine the applicability of fluid models in practical modeling examples. The work is supported by an example where Fluid Models, derived from an higher level modeling language (Fluid Stochastic Petri Nets), have been exploited to study the transfer time distribution in Peer-to-Peer file sharing applications.

Fluid Models in Performance Analysis

GRIBAUDO, MARCO;
2007-01-01

Abstract

Stochastic fluid models have been applied to model and evaluate the performance of many important real systems. The automatic analysis tools to support of fluid models are still not as improved as the ones for discrete state Markov models, but there is a wide range of models which can be effectively described and analyzed with fluid models. Also the model support of hybrid models from various performance evaluation tools improves continuously. The aim of this work is to summarize the basic concepts and the potential use of Markov fluid models. The factors which determine the limits of solvability of fluid models are also discussed. Practical guidelines can be extracted from these factors to determine the applicability of fluid models in practical modeling examples. The work is supported by an example where Fluid Models, derived from an higher level modeling language (Fluid Stochastic Petri Nets), have been exploited to study the transfer time distribution in Peer-to-Peer file sharing applications.
2007
LECTURE NOTES IN ARTIFICIAL INTELLIGENCE
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/569977
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 11
social impact